© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 14086
    Prev
    Next
    INDEX
    Explanations

    references to Adobe software products

    oai_token-act-pair · gpt-3.5-turbo

    references to Adobe software products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ural
    -0.84
    erest
    -0.75
     Pats
    -0.74
    agers
    -0.74
     Ragnarok
    -0.73
    wives
    -0.71
    holm
    -0.67
    urrection
    -0.67
     pronouns
    -0.67
    enger
    -0.67
    POSITIVE LOGITS
    ————
    0.80
     Photoshop
    0.80
    ————————————————
    0.77
    RGB
    0.76
     Adobe
    0.76
    ————————
    0.76
    leck
    0.74
    Kings
    0.72
     Illust
    0.70
    bee
    0.68
    Activations Density 0.080%

    No Known Activations